Fusing Self-Regulated Learning and Machine Learning to Enhance Open and Distance eLearning Systems. A systematic review

There are rapid advancements in the use of digital technologies in Open and Distance eLearning (ODeL) environments worldwide. Digital technologies have significantly enhanced Open and Distance eLearning by improving accessibility, flexibility, and the quality of education. Learners from remote and underserved areas can access educational resources anytime, thereby supporting inclusive education for everyone, regardless of their diverse needs. However, most ODeL systems face challenges such as high student dropouts, low retention rates, and lack of instant instructional and user support. These challenges have given birth to the need for innovative approaches that will enable learner autonomy, motivation, and personalized support. One strategy that ODeL institutions can employ involves combining Self-Regulated Learning (SRL) and Machine Learning (ML) techniques to create intelligent and adaptive learning environments. SRL is very important in ODeL because it allows learners to have control of their own learning by setting metacognitive strategies such as goal setting, strategic planning, self-monitoring, and self-evaluation.  The purpose of this systematic review was to explore the extent to which SRL and ML have been fused to enhance teaching and learning in ODeL contexts. Using a systematic literature review methodology, the study utilized 39 peer-reviewed articles published between 2019 and 2025, drawing on major academic databases, including Google Scholar, SpringerLink, ScienceDirect, IEEE Xplore, and Scopus. This study focused on reviewing studies that implemented ML techniques to model, support, or enhance SRL strategies in ODeL digital learning platforms. Findings from the study indicated that a huge number of studies utilise ML algorithms such as reinforcement learning, natural language processing, supervised learning, and unsupervised clustering in analysing learners’ data and provide adaptive feedback and recommendations that are related to SRL theory. While several studies highlight the effectiveness of ML in enhancing SRL, most are found within structured online courses or intelligent tutoring systems, rather than fully in open or distance learning environments. Furthermore, there is limited research that has focused on the development of ODeL systems that utilise both SRL and Machine Learning to enhance teaching and learning.  This research study concluded by giving coding ideas on how ML and SRL can be combined to enable ODeL institutions to develop Learning Management Systems (LMS) that improve learner engagement, retention, and performance.